transcript-polisher

A transcript-editing workflow for turning spoken recordings into readable documents while keeping the speaker’s meaning and voice.

In plain words
What is it for?
Cleaning podcast, interview, video, or caption transcripts for publication as articles, documents, or show notes.
Why use it?
Automatic transcripts often contain filler words, grammar problems, incomplete sentences, and weak structure.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/cdeistopened/skill-stack/transcript-polisher
Any agent
npx skills add cdeistopened/skill-stack --skill transcript-polisher
Clone the repo
git clone --depth 1 https://github.com/cdeistopened/skill-stack

Made for: Claude Code, Codex.

Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,977 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00060 $0.01977
Opus 5 $0.00030 $0.00988
Sonnet 5 $0.00012 $0.00395
Haiku 4.5 $0.00006 $0.00198

Measured 2d ago against content hash 2dda48747ef3, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

transcript-polisher scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/transcript-polisher/SKILL.md · 283 lines

How it starts

The opening of the file, as written. The whole thing — 283 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Transcript Polisher

Transform raw podcast or interview transcripts into polished, professional documents that maintain authentic voice while dramatically improving readability.

Purpose

Raw transcripts from automated services are often unreadable - filled with filler words, incomplete sentences, and poor formatting. This skill cleans them up while preserving what was actually said.

Core Philosophy: Balance authenticity with clarity. Remove everything that doesn't add meaning while preserving what was actually said. Create the "ideal version" of what the speaker wanted to communicate - without changing their words or ideas.

Target: 25-35% length reduction while maintaining 100% fidelity to meaning.

When to Use This Skill

  • Processing raw transcripts from Rev, Otter, Descript, YouTube auto-captions
  • Cleaning up interview recordings or video transcripts
  • Preparing spoken content for publication as articles or show notes
  • Converting conversational content into readable written format

Not for: Written content that wasn't originally spoken, pre-polished articles, or scripts that are already edited.


Workflow

Step 1: Add Document Structure

Create proper header with:

# [Guest Name]: [Compelling Episode Title]

*[Podcast Name] Episode - [Host Names]*

---

## Timestamped Outline
[Add 10 chapters maximum - see guidelines below]

---

## [Time] Chapter Title
[Content starts here]

Timestamped Outline Rules:

  • Format: **MM:SS** - Descriptive Chapter Title
  • 10 chapters maximum for 45-60 minute episodes
  • Focus on major topic changes, not minute-by-minute
  • Use compelling, specific titles (not generic descriptions)

Good Examples:

  • 12:25 - The Turnaround: From Struggling to Thriving
  • 29:08 - Why Successful Strategies Don't Spread

Poor Examples:

  • 12:25 - Guest talks about their experience
  • 29:08 - Discussion about the industry

Step 2: Identify and Label Speakers

Replace generic speaker markers (>>, Speaker 1, etc.) with actual names:

  • Bold all speaker names: **Isaac:** Content here
  • Use first names for casual podcasts, full names for professional interviews
  • Be consistent throughout

Read the full file on GitHub · 283 lines

Files

What ships with it

3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 283 lines · 60 tokens per session scan A 2dda48747ef3

Subscribe to this mod's changes

transcript-polisher is a skill published in the GitHub repository cdeistopened/skill-stack (27 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,977 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens